# extract-audio

extract-audio pulls sound tracks from video containers using ffmpeg and selects suitable codec presets.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 276 repo stars
- Author: Samarth Gupta
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/gupsammy/Claudest/tree/HEAD/plugins/claude-content/skills/extract-audio/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/extract-audio

## What it does

The skill inspects input files using `ffprobe` and parses stream metadata via an inline Python script. When a clip contains several audio feeds, the assistant asks which one to keep or maps every stream together. If the target format matches the existing track, the tool applies `-c:a copy` to bypass transcoding entirely.

Output options include FLAC, AAC at 192k, variable MP3, constant 128k MP3, or raw WAV at 44100. For video tracks exceeding one hour, the skill offers clipping via `-ss` and `-to` boundaries before running the operation.

Without local `ffmpeg`, `ffprobe`, and Python 3 binaries in your system path, execution fails immediately.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add gupsammy/Claudest
```
In the agent chat (not a shell):
```text
/plugin install claude-content@Claudest
```
This installs the whole claude-content plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add gupsammy/Claudest --skill extract-audio -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/extract-audio/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/extract-audio/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add gupsammy/Claudest --skill extract-audio -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/extract-audio/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add gupsammy/Claudest --skill extract-audio -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/extract-audio/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install gupsammy/Claudest plugins/claude-content/skills/extract-audio
```

2. **Manually: put the files in place**
- File: `.github/skills/extract-audio/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add gupsammy/Claudest --skill extract-audio -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/gupsammy/Claudest --path plugins/claude-content/skills/extract-audio
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/extract-audio/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/gupsammy/Claudest/tree/HEAD/plugins/claude-content/skills/extract-audio/SKILL.md

## When to use it
- pull an uncompressed WAV track from video for DAW editing
- dump speech audio to 128k MP3 for podcast sharing
- copy an existing soundtrack without quality loss or re-encoding
- isolate one specific language stream from a multi-track container

## Example prompts
- Pull the soundtrack from interview.mp4 as a 128k mp3 file
- Rip lossless audio from concert.mkv into a flac file
- Extract the voice track from clip.mov using direct stream copy

## Similar
- [import-audio](https://affpapa.org/en/nevibecode/skills/import-audio.md) — skill · 257 installs
- [audio-mixing](https://affpapa.org/en/nevibecode/skills/audio-mixing.md) — skill · ★ 56 repo stars
- [audio-voice-recovery](https://affpapa.org/en/nevibecode/skills/audio-voice-recovery.md) — skill · 360 installs
- [audio-quality-controller](https://affpapa.org/en/nevibecode/agents/audio-quality-controller.md) — subagent · 547 installs
- [audio-mixing-mastering](https://affpapa.org/en/nevibecode/skills/audio-mixing-mastering.md) — skill · 555 installs
- [scenario-godot-audio](https://affpapa.org/en/nevibecode/skills/scenario-godot-audio.md) — skill · 442 installs

From the same set: [gupsammy/claudest](https://affpapa.org/en/nevibecode/by/gupsammy/claudest.md) — 47 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
